Disclose with Care: Designing Privacy Controls in Interview Chatbots

TL;DR

This paper investigates privacy controls in chatbot interviews on sensitive topics, demonstrating that AI-aided editing effectively reduces personal information disclosure while preserving data quality and engagement.

Contribution

It introduces and evaluates AI-aided editing as a novel privacy control mechanism in chatbot interviews, balancing ethical concerns and data integrity.

Findings

AI-aided editing reduces PII disclosure

Participants remain engaged with AI-aided editing

Privacy controls can balance ethics and data quality

Abstract

Collecting data on sensitive topics remains challenging in HCI, as participants often withhold information due to privacy concerns and social desirability bias. While chatbots' perceived anonymity may reduce these barriers, research paradoxically suggests people tend to over-share personal or sensitive information with chatbots. In this work, we explore privacy controls in chatbot interviews to address this problem. The privacy control allows participants to revise their transcripts at the end of the interview, featuring two design variants: free editing and AI-aided editing. In a between-subjects study \red{($N=188$)}, we compared no-editing, free-editing, and AI-aided editing conditions in a chatbot-based interview on a sensitive topic. Our results confirm the prevalent issue of oversharing in chatbot-based interviews and show that AI-aided editing serves as an effective privacy-control mechanism, reducing PII disclosure while maintaining data quality and user engagement, thereby offering a promising approach to balancing ethical practice and data quality in such interviews.